| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1, | |
| "eval_steps": 500, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025, | |
| "grad_norm": 28.533191680908203, | |
| "learning_rate": 0.00019950000000000002, | |
| "loss": 10.2028, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005, | |
| "grad_norm": 1.5962224006652832, | |
| "learning_rate": 0.000199, | |
| "loss": 1.8731, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0075, | |
| "grad_norm": 0.8784465193748474, | |
| "learning_rate": 0.00019850000000000003, | |
| "loss": 0.5834, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.6551746726036072, | |
| "learning_rate": 0.00019800000000000002, | |
| "loss": 0.4274, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0125, | |
| "grad_norm": 0.7458402514457703, | |
| "learning_rate": 0.00019750000000000003, | |
| "loss": 0.2921, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.015, | |
| "grad_norm": 0.6910417675971985, | |
| "learning_rate": 0.00019700000000000002, | |
| "loss": 0.1889, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0175, | |
| "grad_norm": 0.575136125087738, | |
| "learning_rate": 0.0001965, | |
| "loss": 0.1379, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.2535680532455444, | |
| "learning_rate": 0.000196, | |
| "loss": 0.1053, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0225, | |
| "grad_norm": 0.9697864651679993, | |
| "learning_rate": 0.0001955, | |
| "loss": 0.0756, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 0.508269727230072, | |
| "learning_rate": 0.000195, | |
| "loss": 0.055, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0275, | |
| "grad_norm": 0.6621774435043335, | |
| "learning_rate": 0.0001945, | |
| "loss": 0.0487, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.5406679511070251, | |
| "learning_rate": 0.000194, | |
| "loss": 0.0406, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0325, | |
| "grad_norm": 0.35967350006103516, | |
| "learning_rate": 0.00019350000000000001, | |
| "loss": 0.0347, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.035, | |
| "grad_norm": 0.6122244000434875, | |
| "learning_rate": 0.000193, | |
| "loss": 0.0334, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0375, | |
| "grad_norm": 0.4679579734802246, | |
| "learning_rate": 0.00019250000000000002, | |
| "loss": 0.0342, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.6229879856109619, | |
| "learning_rate": 0.000192, | |
| "loss": 0.0328, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0425, | |
| "grad_norm": 0.4741787314414978, | |
| "learning_rate": 0.00019150000000000002, | |
| "loss": 0.0328, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.045, | |
| "grad_norm": 0.3581089377403259, | |
| "learning_rate": 0.000191, | |
| "loss": 0.0329, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0475, | |
| "grad_norm": 0.2805705964565277, | |
| "learning_rate": 0.00019050000000000002, | |
| "loss": 0.0316, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.36797094345092773, | |
| "learning_rate": 0.00019, | |
| "loss": 0.0314, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0525, | |
| "grad_norm": 0.22872206568717957, | |
| "learning_rate": 0.0001895, | |
| "loss": 0.0304, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.055, | |
| "grad_norm": 0.3525296151638031, | |
| "learning_rate": 0.00018899999999999999, | |
| "loss": 0.0315, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.0575, | |
| "grad_norm": 0.21026159822940826, | |
| "learning_rate": 0.0001885, | |
| "loss": 0.0302, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.1741417497396469, | |
| "learning_rate": 0.000188, | |
| "loss": 0.0307, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 0.35116010904312134, | |
| "learning_rate": 0.0001875, | |
| "loss": 0.0305, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.065, | |
| "grad_norm": 0.2572971284389496, | |
| "learning_rate": 0.00018700000000000002, | |
| "loss": 0.0313, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.0675, | |
| "grad_norm": 0.2466694414615631, | |
| "learning_rate": 0.0001865, | |
| "loss": 0.0299, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.19943873584270477, | |
| "learning_rate": 0.00018600000000000002, | |
| "loss": 0.0304, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.0725, | |
| "grad_norm": 0.3378709852695465, | |
| "learning_rate": 0.0001855, | |
| "loss": 0.0299, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": 0.23438668251037598, | |
| "learning_rate": 0.00018500000000000002, | |
| "loss": 0.0301, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.0775, | |
| "grad_norm": 0.3201534152030945, | |
| "learning_rate": 0.0001845, | |
| "loss": 0.0307, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.19868455827236176, | |
| "learning_rate": 0.00018400000000000003, | |
| "loss": 0.0294, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.0825, | |
| "grad_norm": 0.20487827062606812, | |
| "learning_rate": 0.00018350000000000002, | |
| "loss": 0.0309, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.085, | |
| "grad_norm": 0.3057793378829956, | |
| "learning_rate": 0.000183, | |
| "loss": 0.0307, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.0875, | |
| "grad_norm": 0.12229125201702118, | |
| "learning_rate": 0.0001825, | |
| "loss": 0.0303, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.18177232146263123, | |
| "learning_rate": 0.000182, | |
| "loss": 0.0302, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.0925, | |
| "grad_norm": 0.28575578331947327, | |
| "learning_rate": 0.0001815, | |
| "loss": 0.0304, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.095, | |
| "grad_norm": 0.19034205377101898, | |
| "learning_rate": 0.000181, | |
| "loss": 0.03, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.0975, | |
| "grad_norm": 0.23103861510753632, | |
| "learning_rate": 0.0001805, | |
| "loss": 0.0305, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.15927983820438385, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0292, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 4000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 440449577779200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |